whatmodel.sh / Claude Opus 5.5

Claude Opus 5.5

+ contribute

Claude Opus 5.5 is a closed-weights language model from Anthropic, released September 2026.

86.9±0.7#2 of 719 LLMsfrom 28 benchmark results across 7 sources

$ how it compares

The LLMs ranked either side of Claude Opus 5.5, out of 828 with a score, then more from Anthropic.

#	model	score	where	released
1	GPT-6 Astra OpenAI	87±1	api $20.00/M	2026-09
2	Claude Opus 5.5 Anthropic	87±1	api $8.00/M	2026-09
3	GPT-6.1 Sol OpenAI	85±1	api $4.00/M	2026-09
4	Claude Fable 5.1 Anthropic	85±1	api $20.00/M	2026-09
5	Claude Sonnet 5.5 Anthropic	84±1	api $4.00/M	2026-09
	more from Anthropic
6	Claude Opus 5 Anthropic	83±1	api $10.00/M	2026-07
11	Claude Fable 5 Anthropic	81±1	api $20.00/M	2026-06
12	Claude Mythos Preview (limited preview) Anthropic	81±1	limited preview	2026-04

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▃ #1 of 300 · 38% of its score · 9 tests

Beats GPT-6 Astra here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Terminal-Bench 4.0 +1	64.8% ✎	█▅▅▅▅·▅▃▃▅▅▅ beats 20/20	very hard · avg 0.4%	▇▇▇▇▇ 12%	sharp · at its level · several runs
Arena Agent (October 2026 aggregate IPS)	0.1382 IPS ✎	▁▁▁▄▂▃▇█▂▂▁▃ beats 48/49	avg -0.312 IPS	▇▇▇ 8.4%	sharp
SWE-bench Pro (split unspecified) lab	89.9% ✎	▄█·▄·▄██···▄ beats 9/9	very hard · avg 7.6%	▇▇ 5.5%	sharp
SWE-bench Multilingual lab	93.9% ✎	▃··▃·▅▃▃█··▃ beats 9/9	hard · avg 31%	▇ 2.8%	maxed out
Humanity's Last Exam with tools lab	67.7% ✎	▁······▁·▄·█ beats 10/10	very hard · avg 14%	▇ 2.3%	at its level
DeepSWE v1.1 (resolved) lab	74.2% ✎	█·····████·█ beats 5/5	hard · avg 18%	▇ 2.0%	at its level
Chartography with tools lab	89.0% ✎	▃········▃██ beats 6/7	very hard · avg 4.7%	▇ 2.0%	sharp
KlinikeBench strict pass@1 (333 interactive clinical encounters, Terminus-2)	28.8% ✎	▁▁·▁▁▁▁▅▃█▅█ beats 26/27	very hard · avg 2.4%	▇ 1.9%	at its level

1 more test

test	result	vs the others in its run	difficulty	counts	why
Toolathlon-Verified lab	77.8% ✎	▃·····█···▃▃ beats 3/5	hard · avg 35%	▇ 1.0%	blunt

coding▁▁▁▃▆██▇▆▄▃▃ #1 of 458 · 19% of its score · 5 tests

Beats GPT-6 Astra here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Arena WebDev (Code Arena)	1815.4 ✎	▁▂▄▃▅█▄▇▆▄▁▃ beats 119/119	avg 981	▇▇▇ 7.4%	sharp
SWE-bench Pro (split unspecified) lab	89.9% ✎	▄█·▄·▄██···▄ beats 9/9	very hard · avg 7.6%	▇▇ 5.5%	sharp
SWE-bench Multilingual lab	93.9% ✎	▃··▃·▅▃▃█··▃ beats 9/9	hard · avg 31%	▇ 2.8%	maxed out
DeepSWE v1.1 (resolved) lab	74.2% ✎	█·····████·█ beats 5/5	hard · avg 18%	▇ 2.0%	at its level
Luau Leetcode fully solved (Torpedo Software)	87.0% ✎	▁▁▁▁·▁▂▃▅▃█▇ beats 49/49	hard · avg 18%	▇ 1.3%	typical

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #4 of 393 * · 4.2% of its score · 1 test

Beats GPT-6 Astra here, though they rank higher overall. Trails Claude Opus 4.6, Claude Fable 5, Gemini 4 Argon (limited preview) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
LMArena (text)	1503.7 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 376/379	avg 1268	▇▇ 4.2%	blunt

math▁▂▃▅▆▅▄█▄▁▁▃ #3 of 398 · 12% of its score · 4 tests

Trails GPT-6.1 Sol here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
FrontierMath tier 4 v2	95.0% ✎	▁▂▁▂█▅▂▂▁▃▁▁ beats 61/63	very hard · avg 0.1%	▇▇▇ 6.6%	sharp
FrontierMath tiers 1–3 v2	91.2% ✎	▂··▁▁▃▄▄█▅▃▃ beats 80/82	very hard · avg 1.2%	▇▇ 4.4%	sharp · maxed out
FrontierMath: Erdős problems	2.9% ✎	█··········▆ beats 5/6	very hard · avg 0.0%	▇ 1.0%	sharp · too hard for it · noisy
OTIS mock AIME 2024–2025	100.0% ✎	▃▃▄▃▃▃▇▇█▃▂▅ beats 184/193	very hard · avg 8.5%	▇ 0.1%	sharp · maxed out · noisy

web search▂▁▂▆▄█▃▃▁▁·▁ #12 of 80 * · 2.3% of its score · 1 test

Trails GPT-4o mini (2024-07-18), Mistral Small 3.1 24B (2503), GPT-4o (2024-08-06) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Humanity's Last Exam with tools lab	67.7% ✎	▁······▁·▄·█ beats 10/10	very hard · avg 14%	▇ 2.3%	at its level

other tests11 not in a task · 37% of its score

test	result	vs the others in its run	difficulty	counts	why
EBR-bench (Epoch)	71.4% ✎	▄▂·▆█▂▆▄▆▆·▄ beats 22/23	very hard · avg 0.3%	▇▇▇▇▇ 12%	sharp · at its level
Mystery Game Puzzles (Epoch)	71.0% ✎	█··▂▃▇▄█▂▃▃▁ beats 72/74	very hard · avg 9.4%	▇▇▇ 6.9%	sharp · at its level · noisy
Furniture Assembly (Epoch)	83.3% ✎	█▆▆▆▆▂▅▂▂▂·▅ beats 30/30	very hard · avg 1.2%	▇▇▇ 6.3%	sharp · at its level
Humanity's Last Exam lab	64.4% ✎	▂·····▂·▄▂█▄ beats 10/10	very hard · avg 5.8%	▇▇ 4.7%	at its level
Global-MMLU lab	94.3% ✎	▄▄····▄▄··▄█ beats 6/6	medium · avg 63%	▇ 1.6%	maxed out
SimpleQA Verified	72.2% ✎	▁▁▃▂▃▃▆▆█▃▂▅ beats 75/78	very hard · avg 8.0%	▇ 1.4%	at its level
Icelandic LLM Leaderboard average (Miðeind, Sept 2026 suite)	70.9% ✎	▁▁▃▂▂▄▁▃▄▄▄█ beats 38/38	very hard · avg 14%	▇ 1.2%	at its level
MirrorCode (Epoch)	77.4% ✎	█·▄▄·▄·▄·▄·█ beats 8/8	very hard · avg 1.5%	▇ 1.1%	sharp · at its level · noisy

3 more tests

test	result	vs the others in its run	difficulty	counts	why
HealthBench lab	68.1% ✎	█·▄·····▄▄▄▄ beats 5/6	hard · avg 29%	▇ 1.0%	blunt · at its level
GPQA Diamond	90.6% ✎	▁▁▁▁▂▄▆▄▅▇█▅ beats 176/208	hard · avg 40%	▇ 0.8%	sharp · maxed out
RobloxQA v2.0 multiple choice (Torpedo Software)	98.6% ✎	▁▁▃▁█▄▃▃▆▂▂▃ beats 49/49	easy · avg 78%	▇ 0.5%	maxed out

$ where to run it

Through an API

api · $8.00/M · $4 in / $20 out per 1M tokens · 1M context · docs.anthropic.com ↗ · price sourceStandard base token rate from models.dev. Provider-specific tiers, long-context surcharges, caching and promotions may differ.

$ how the score was worked out · Epoch AI — internal evaluatio… 40%, Anthropic system cards and mo… 29%, LMArena leaderboard dataset 20% and 4 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
Epoch AI — internal evaluations	10	▇▇▇▇▇▇▇▇▇▇▇▇ 40%	CC BY 4.0
Anthropic system cards and model announcements (lab-reported scores) · lab-reported	10	▇▇▇▇▇▇▇▇▇ 29%	Factual vendor-reported score (not licensed content)
LMArena leaderboard dataset	3	▇▇▇▇▇▇ 20%	CC BY 4.0
Terminal-Bench 4.0 official leaderboard submissions	1	▇▇ 6%	Apache-2.0
KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arXiv:2609.38480v2)	1	▇ 2%	CC BY 4.0
Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode	2	▇ 2%	MIT
Miðeind Icelandic LLM Leaderboard	1	▇ 1%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 86.9